Error reading geopackage data in Azure Databricks #1718
Comments
|
Thank you for your interest in Apache Sedona! We appreciate you opening your first issue. Contributions like yours help make Apache Sedona better. |
|
@Imbruced can you take a look? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Expected behavior
Load geopackage data to a dataframe in Azure Databricks Notebook
Actual behavior
Error reading geopackage data. Exception stacktrace below
Steps to reproduce the problem
In a notebook
Settings
Sedona version = 1.7.0
Apache Spark version = 3.5.0
Azure Databricks version = 15.4 LTS
Cluster type = single user personal cluster
Use Photon = false
Worker type = Standard_D4ds_v5
API type = Python
Scala version = 2.12
JRE version = zulu8-ca-amd64
Python version = 3.11
Py4JJavaError: An error occurred while calling t.addCustomDisplayData. : java.lang.ClassCastException: org.apache.spark.sql.execution.datasources.SerializableFileStatus cannot be cast to org.apache.hadoop.fs.FileStatus at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:286) at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62) at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49) at scala.collection.TraversableLike.map(TraversableLike.scala:286) at scala.collection.TraversableLike.map$(TraversableLike.scala:279) at scala.collection.AbstractTraversable.map(Traversable.scala:108) at org.apache.sedona.sql.datasources.geopackage.GeoPackageScanBuilder.build(GeoPackageScanBuilder.scala:40) at org.apache.spark.sql.execution.datasources.v2.PushDownUtils$.pruneColumns(PushDownUtils.scala:229) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$$anonfun$pruneColumns$1.applyOrElse(V2ScanRelationPushDown.scala:369) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$$anonfun$pruneColumns$1.applyOrElse(V2ScanRelationPushDown.scala:360) at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:505) at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(origin.scala:85) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:505) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:379) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:375) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$3(TreeNode.scala:510) at org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren(TreeNode.scala:1314) at org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren$(TreeNode.scala:1313) at org.apache.spark.sql.catalyst.plans.logical.LocalLimit.mapChildren(basicLogicalOperators.scala:2010) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:510) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:379) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:375) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$3(TreeNode.scala:510) at org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren(TreeNode.scala:1314) at org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren$(TreeNode.scala:1313) at org.apache.spark.sql.catalyst.plans.logical.GlobalLimit.mapChildren(basicLogicalOperators.scala:1989) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:510) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:379) at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:375) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:40) at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:481) at org.apache.spark.sql.catalyst.trees.TreeNode.transform(TreeNode.scala:449) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.pruneColumns(V2ScanRelationPushDown.scala:360) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.$anonfun$apply$7(V2ScanRelationPushDown.scala:54) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.$anonfun$apply$8(V2ScanRelationPushDown.scala:57) at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126) at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122) at scala.collection.immutable.List.foldLeft(List.scala:91) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.apply(V2ScanRelationPushDown.scala:56) at org.apache.spark.sql.execution.datasources.v2.V2ScanRelationPushDown$.apply(V2ScanRelationPushDown.scala:43) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$4(RuleExecutor.scala:327) at com.databricks.spark.util.FrameProfiler$.record(FrameProfiler.scala:94) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$3(RuleExecutor.scala:327) at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126) at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122) at scala.collection.immutable.List.foldLeft(List.scala:91) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:324) at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23) at com.databricks.spark.util.FrameProfiler$.record(FrameProfiler.scala:94) at org.apache.spark.sql.catalyst.rules.RuleExecutor.executeBatch$1(RuleExecutor.scala:307) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$9(RuleExecutor.scala:411) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$9$adapted(RuleExecutor.scala:411) at scala.collection.immutable.List.foreach(List.scala:431) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:411) at com.databricks.spark.util.FrameProfiler$.record(FrameProfiler.scala:94) at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:270) at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:262) at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:178) at org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:262) at org.apache.spark.sql.execution.QueryExecution.$anonfun$optimizedPlan$2(QueryExecution.scala:459) at com.databricks.spark.util.FrameProfiler$.record(FrameProfiler.scala:94) at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:454) at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$5(QueryExecution.scala:613) at org.apache.spark.sql.execution.SQLExecution$.withExecutionPhase(SQLExecution.scala:144) at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$4(QueryExecution.scala:613) at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:1177) at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$2(QueryExecution.scala:612) at com.databricks.util.LexicalThreadLocal$Handle.runWith(LexicalThreadLocal.scala:63) at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:608) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:1180) at org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:608) at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:455) at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:442) at org.apache.spark.sql.execution.QueryExecution.assertOptimized(QueryExecution.scala:469) at org.apache.spark.sql.execution.QueryExecution._executedPlan$lzycompute(QueryExecution.scala:502) at org.apache.spark.sql.execution.QueryExecution._executedPlan(QueryExecution.scala:499) at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:573) at org.apache.spark.sql.execution.QueryExecution.simpleString(QueryExecution.scala:667) at org.apache.spark.sql.execution.QueryExecution.org$apache$spark$sql$execution$QueryExecution$$explainString(QueryExecution.scala:733) at org.apache.spark.sql.execution.QueryExecution.explainStringLocal(QueryExecution.scala:695) at org.apache.spark.sql.execution.QueryExecution.explainString(QueryExecution.scala:688) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId0$10(SQLExecution.scala:394) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:800) at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId0$1(SQLExecution.scala:334) at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:1180) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId0(SQLExecution.scala:205) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:737) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4805) at org.apache.spark.sql.Dataset.collectResult(Dataset.scala:3834) at com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation0(OutputAggregator.scala:325) at com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation(OutputAggregator.scala:101) at com.databricks.backend.daemon.driver.PythonDriverLocalBase.generateTableResult(PythonDriverLocalBase.scala:876) at com.databricks.backend.daemon.driver.JupyterDriverLocal.computeListResultsItem(JupyterDriverLocal.scala:1576) at com.databricks.backend.daemon.driver.JupyterDriverLocal$JupyterEntryPoint.addCustomDisplayData(JupyterDriverLocal.scala:287) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:397) at py4j.Gateway.invoke(Gateway.java:306) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.ClientServerConnection.waitForCommands(ClientServerConnection.java:199) at py4j.ClientServerConnection.run(ClientServerConnection.java:119) at java.lang.Thread.run(Thread.java:750)
File , line 1 ----> 1 display(bag)
File /databricks/python_shell/dbruntime/display.py:148, in Display.display(self, input, *args, **kwargs) 145 if kwargs.get('trigger'): 146 raise Exception('Triggers can only be set for streaming queries.') --> 148 self.add_custom_display_data("table", input._jdf) 149 elif isinstance(input, list): 150 self.display(self.sparkSession.createDataFrame(input))
File /databricks/python_shell/dbruntime/display.py:72, in Display.add_custom_display_data(self, data_type, data) 70 def add_custom_display_data(self, data_type, data): 71 custom_display_key = str(uuid.uuid4()) ---> 72 return_code = self.entry_point.addCustomDisplayData(custom_display_key, data_type, data) 73 ip_display({ 74 "application/vnd.databricks.v1+display": custom_display_key, 75 "text/plain": "<Databricks Output (not supported in output widgets)>" 76 }, 77 raw=True) 78 if return_code == 1:
File /databricks/spark/python/lib/py4j-0.10.9.7-src.zip/py4j/java_gateway.py:1355, in JavaMember.call(self, *args) 1349 command = proto.CALL_COMMAND_NAME +\ 1350 self.command_header +\ 1351 args_command +\ 1352 proto.END_COMMAND_PART 1354 answer = self.gateway_client.send_command(command) -> 1355 return_value = get_return_value( 1356 answer, self.gateway_client, self.target_id, self.name) 1358 for temp_arg in temp_args: 1359 if hasattr(temp_arg, "_detach"):
File /databricks/spark/python/pyspark/errors/exceptions/captured.py:255, in capture_sql_exception..deco(*a, **kw) 252 from py4j.protocol import Py4JJavaError 254 try: --> 255 return f(*a, **kw) 256 except Py4JJavaError as e: 257 converted = convert_exception(e.java_exception)
File /databricks/spark/python/lib/py4j-0.10.9.7-src.zip/py4j/protocol.py:326, in get_return_value(answer, gateway_client, target_id, name) 324 value = OUTPUT_CONVERTER[type](answer[2:], gateway_client) 325 if answer[1] == REFERENCE_TYPE: --> 326 raise Py4JJavaError( 327 "An error occurred while calling {0}{1}{2}.\n". 328 format(target_id, ".", name), value) 329 else: 330 raise Py4JError( 331 "An error occurred while calling {0}{1}{2}. Trace:\n{3}\n". 332 format(target_id, ".", name, value))
The text was updated successfully, but these errors were encountered: